Feat/add-remote-file-upload-api (#9906)

api/controllers/common/errors.py

@@ -0,0 +1,6 @@
+from werkzeug.exceptions import HTTPException
+
+
+class FilenameNotExistsError(HTTPException):
+    code = 400
+    description = "The specified filename does not exist."

api/controllers/common/helpers.py

@@ -0,0 +1,58 @@
+import mimetypes
+import os
+import re
+import urllib.parse
+from uuid import uuid4
+
+import httpx
+from pydantic import BaseModel
+
+
+class FileInfo(BaseModel):
+    filename: str
+    extension: str
+    mimetype: str
+    size: int
+
+
+def guess_file_info_from_response(response: httpx.Response):
+    url = str(response.url)
+    # Try to extract filename from URL
+    parsed_url = urllib.parse.urlparse(url)
+    url_path = parsed_url.path
+    filename = os.path.basename(url_path)
+
+    # If filename couldn't be extracted, use Content-Disposition header
+    if not filename:
+        content_disposition = response.headers.get("Content-Disposition")
+        if content_disposition:
+            filename_match = re.search(r'filename="?(.+)"?', content_disposition)
+            if filename_match:
+                filename = filename_match.group(1)
+
+    # If still no filename, generate a unique one
+    if not filename:
+        unique_name = str(uuid4())
+        filename = f"{unique_name}"
+
+    # Guess MIME type from filename first, then URL
+    mimetype, _ = mimetypes.guess_type(filename)
+    if mimetype is None:
+        mimetype, _ = mimetypes.guess_type(url)
+    if mimetype is None:
+        # If guessing fails, use Content-Type from response headers
+        mimetype = response.headers.get("Content-Type", "application/octet-stream")
+
+    extension = os.path.splitext(filename)[1]
+
+    # Ensure filename has an extension
+    if not extension:
+        extension = mimetypes.guess_extension(mimetype) or ".bin"
+        filename = f"{filename}{extension}"
+
+    return FileInfo(
+        filename=filename,
+        extension=extension,
+        mimetype=mimetype,
+        size=int(response.headers.get("Content-Length", -1)),
+    )

api/controllers/console/__init__.py

@@ -2,9 +2,21 @@ from flask import Blueprint
 
 from libs.external_api import ExternalApi
 
+from .files import FileApi, FilePreviewApi, FileSupportTypeApi
+from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
+
 bp = Blueprint("console", __name__, url_prefix="/console/api")
 api = ExternalApi(bp)
 
+# File
+api.add_resource(FileApi, "/files/upload")
+api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
+api.add_resource(FileSupportTypeApi, "/files/support-type")
+
+# Remote files
+api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
+api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
+
 # Import other controllers
 from . import admin, apikey, extension, feature, ping, setup, version
 
@@ -43,7 +55,6 @@ from .datasets import (
     datasets_document,
     datasets_segments,
     external,
-    file,
     hit_testing,
     website,
 )

api/controllers/console/apikey.py

@@ -10,8 +10,7 @@ from models.dataset import Dataset
 from models.model import ApiToken, App
 
 from . import api
-from .setup import setup_required
-from .wraps import account_initialization_required
+from .wraps import account_initialization_required, setup_required
 
 api_key_fields = {
     "id": fields.String,

api/controllers/console/app/advanced_prompt_template.py

@@ -1,8 +1,7 @@
 from flask_restful import Resource, reqparse
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.advanced_prompt_template_service import AdvancedPromptTemplateService
 

api/controllers/console/app/agent.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.helper import uuid_value
 from libs.login import login_required
 from models.model import AppMode

api/controllers/console/app/annotation.py

@@ -6,8 +6,11 @@ from werkzeug.exceptions import Forbidden
 from controllers.console import api
 from controllers.console.app.error import NoFileUploadedError
 from controllers.console.datasets.error import TooManyFilesError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from extensions.ext_redis import redis_client
 from fields.annotation_fields import (
     annotation_fields,

api/controllers/console/app/app.py

@@ -6,8 +6,11 @@ from werkzeug.exceptions import BadRequest, Forbidden, abort
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.ops.ops_trace_manager import OpsTraceManager
 from fields.app_fields import (
     app_detail_fields,

api/controllers/console/app/audio.py

@@ -18,8 +18,7 @@ from controllers.console.app.error import (
     UnsupportedAudioTypeError,
 )
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError
 from libs.login import login_required

api/controllers/console/app/completion.py

@@ -15,8 +15,7 @@ from controllers.console.app.error import (
     ProviderQuotaExceededError,
 )
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from controllers.web.error import InvokeRateLimitError as InvokeRateLimitHttpError
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom

api/controllers/console/app/conversation.py

@@ -10,8 +10,7 @@ from werkzeug.exceptions import Forbidden, NotFound
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.app.entities.app_invoke_entities import InvokeFrom
 from extensions.ext_database import db
 from fields.conversation_fields import (

api/controllers/console/app/conversation_variables.py

@@ -4,8 +4,7 @@ from sqlalchemy.orm import Session
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from fields.conversation_variable_fields import paginated_conversation_variable_fields
 from libs.login import login_required

api/controllers/console/app/generator.py

@@ -10,8 +10,7 @@ from controllers.console.app.error import (
     ProviderNotInitializeError,
     ProviderQuotaExceededError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.llm_generator.llm_generator import LLMGenerator
 from core.model_runtime.errors.invoke import InvokeError

api/controllers/console/app/message.py

@@ -14,8 +14,11 @@ from controllers.console.app.error import (
 )
 from controllers.console.app.wraps import get_app_model
 from controllers.console.explore.error import AppSuggestedQuestionsAfterAnswerDisabledError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.app.entities.app_invoke_entities import InvokeFrom
 from core.errors.error import ModelCurrentlyNotSupportError, ProviderTokenNotInitError, QuotaExceededError
 from core.model_runtime.errors.invoke import InvokeError

api/controllers/console/app/model_config.py

@@ -6,8 +6,7 @@ from flask_restful import Resource
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.agent.entities import AgentToolEntity
 from core.tools.tool_manager import ToolManager
 from core.tools.utils.configuration import ToolParameterConfigurationManager

api/controllers/console/app/ops_trace.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.error import TracingConfigCheckError, TracingConfigIsExist, TracingConfigNotExist
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.ops_service import OpsService
 

api/controllers/console/app/site.py

@@ -7,8 +7,7 @@ from werkzeug.exceptions import Forbidden, NotFound
 from constants.languages import supported_language
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from fields.app_fields import app_site_fields
 from libs.login import login_required

api/controllers/console/app/statistic.py

@@ -8,8 +8,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required

api/controllers/console/app/workflow.py

@@ -9,8 +9,7 @@ import services
 from controllers.console import api
 from controllers.console.app.error import ConversationCompletedError, DraftWorkflowNotExist, DraftWorkflowNotSync
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.app.apps.base_app_queue_manager import AppQueueManager
 from core.app.entities.app_invoke_entities import InvokeFrom
 from factories import variable_factory

api/controllers/console/app/workflow_app_log.py

@@ -3,8 +3,7 @@ from flask_restful.inputs import int_range
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.workflow_app_log_fields import workflow_app_log_pagination_fields
 from libs.login import login_required
 from models import App

api/controllers/console/app/workflow_run.py

@@ -3,8 +3,7 @@ from flask_restful.inputs import int_range
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.workflow_run_fields import (
     advanced_chat_workflow_run_pagination_fields,
     workflow_run_detail_fields,

api/controllers/console/app/workflow_statistic.py

@@ -8,8 +8,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.app.wraps import get_app_model
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from libs.helper import DatetimeString
 from libs.login import login_required

api/controllers/console/auth/data_source_bearer_auth.py

@@ -7,8 +7,7 @@ from controllers.console.auth.error import ApiKeyAuthFailedError
 from libs.login import login_required
 from services.auth.api_key_auth_service import ApiKeyAuthService
 
-from ..setup import setup_required
-from ..wraps import account_initialization_required
+from ..wraps import account_initialization_required, setup_required
 
 
 class ApiKeyAuthDataSource(Resource):

api/controllers/console/auth/data_source_oauth.py

@@ -11,8 +11,7 @@ from controllers.console import api
 from libs.login import login_required
 from libs.oauth_data_source import NotionOAuth
 
-from ..setup import setup_required
-from ..wraps import account_initialization_required
+from ..wraps import account_initialization_required, setup_required
 
 
 def get_oauth_providers():

api/controllers/console/auth/forgot_password.py

@@ -13,7 +13,7 @@ from controllers.console.auth.error import (
     PasswordMismatchError,
 )
 from controllers.console.error import EmailSendIpLimitError, NotAllowedRegister
-from controllers.console.setup import setup_required
+from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from extensions.ext_database import db
 from libs.helper import email, extract_remote_ip

api/controllers/console/auth/login.py

@@ -20,7 +20,7 @@ from controllers.console.error import (
     NotAllowedCreateWorkspace,
     NotAllowedRegister,
 )
-from controllers.console.setup import setup_required
+from controllers.console.wraps import setup_required
 from events.tenant_event import tenant_was_created
 from libs.helper import email, extract_remote_ip
 from libs.password import valid_password

api/controllers/console/billing/billing.py

@@ -2,8 +2,7 @@ from flask_login import current_user
 from flask_restful import Resource, reqparse
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, only_edition_cloud
+from controllers.console.wraps import account_initialization_required, only_edition_cloud, setup_required
 from libs.login import login_required
 from services.billing_service import BillingService
 

api/controllers/console/datasets/data_source.py

@@ -7,8 +7,7 @@ from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import NotFound
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.indexing_runner import IndexingRunner
 from core.rag.extractor.entity.extract_setting import ExtractSetting
 from core.rag.extractor.notion_extractor import NotionExtractor

api/controllers/console/datasets/datasets.py

@@ -10,8 +10,7 @@ from controllers.console import api
 from controllers.console.apikey import api_key_fields, api_key_list
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import DatasetInUseError, DatasetNameDuplicateError, IndexingEstimateError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.indexing_runner import IndexingRunner
 from core.model_runtime.entities.model_entities import ModelType

api/controllers/console/datasets/datasets_document.py

@@ -24,8 +24,11 @@ from controllers.console.datasets.error import (
     InvalidActionError,
     InvalidMetadataError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from core.errors.error import (
     LLMBadRequestError,
     ModelCurrentlyNotSupportError,

api/controllers/console/datasets/datasets_segments.py

@@ -11,11 +11,11 @@ import services
 from controllers.console import api
 from controllers.console.app.error import ProviderNotInitializeError
 from controllers.console.datasets.error import InvalidActionError, NoFileUploadedError, TooManyFilesError
-from controllers.console.setup import setup_required
 from controllers.console.wraps import (
     account_initialization_required,
     cloud_edition_billing_knowledge_limit_check,
     cloud_edition_billing_resource_check,
+    setup_required,
 )
 from core.errors.error import LLMBadRequestError, ProviderTokenNotInitError
 from core.model_manager import ModelManager

api/controllers/console/datasets/external.py

@@ -6,8 +6,7 @@ from werkzeug.exceptions import Forbidden, InternalServerError, NotFound
 import services
 from controllers.console import api
 from controllers.console.datasets.error import DatasetNameDuplicateError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.dataset_fields import dataset_detail_fields
 from libs.login import login_required
 from services.dataset_service import DatasetService

api/controllers/console/datasets/hit_testing.py

@@ -2,8 +2,7 @@ from flask_restful import Resource
 
 from controllers.console import api
 from controllers.console.datasets.hit_testing_base import DatasetsHitTestingBase
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 
 

api/controllers/console/datasets/website.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 
 from controllers.console import api
 from controllers.console.datasets.error import WebsiteCrawlError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from libs.login import login_required
 from services.website_service import WebsiteService
 

api/controllers/console/extension.py

@@ -3,8 +3,7 @@ from flask_restful import Resource, marshal_with, reqparse
 
 from constants import HIDDEN_VALUE
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.api_based_extension_fields import api_based_extension_fields
 from libs.login import login_required
 from models.api_based_extension import APIBasedExtension

api/controllers/console/feature.py

@@ -5,8 +5,7 @@ from libs.login import login_required
 from services.feature_service import FeatureService
 
 from . import api
-from .setup import setup_required
-from .wraps import account_initialization_required, cloud_utm_record
+from .wraps import account_initialization_required, cloud_utm_record, setup_required
 
 
 class FeatureApi(Resource):

api/controllers/console/files/__init__.py

@@ -1,25 +1,26 @@
-import urllib.parse
-
 from flask import request
 from flask_login import current_user
-from flask_restful import Resource, marshal_with, reqparse
+from flask_restful import Resource, marshal_with
 
 import services
 from configs import dify_config
 from constants import DOCUMENT_EXTENSIONS
-from controllers.console import api
-from controllers.console.datasets.error import (
+from controllers.common.errors import FilenameNotExistsError
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
+from fields.file_fields import file_fields, upload_config_fields
+from libs.login import login_required
+from services.file_service import FileService
+
+from .errors import (
     FileTooLargeError,
     NoFileUploadedError,
     TooManyFilesError,
     UnsupportedFileTypeError,
 )
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
-from core.helper import ssrf_proxy
-from fields.file_fields import file_fields, remote_file_info_fields, upload_config_fields
-from libs.login import login_required
-from services.file_service import FileService
 
 PREVIEW_WORDS_LIMIT = 3000
 
@@ -44,21 +45,29 @@ class FileApi(Resource):
     @marshal_with(file_fields)
     @cloud_edition_billing_resource_check("documents")
     def post(self):
-        # get file from request
         file = request.files["file"]
+        source = request.form.get("source")
 
-        parser = reqparse.RequestParser()
-        parser.add_argument("source", type=str, required=False, location="args")
-        source = parser.parse_args().get("source")
-
-        # check file
         if "file" not in request.files:
             raise NoFileUploadedError()
 
         if len(request.files) > 1:
             raise TooManyFilesError()
+
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        if source not in ("datasets", None):
+            source = None
+
         try:
-            upload_file = FileService.upload_file(file=file, user=current_user, source=source)
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+                source=source,
+            )
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:
@@ -83,23 +92,3 @@ class FileSupportTypeApi(Resource):
     @account_initialization_required
     def get(self):
         return {"allowed_extensions": DOCUMENT_EXTENSIONS}
-
-
-class RemoteFileInfoApi(Resource):
-    @marshal_with(remote_file_info_fields)
-    def get(self, url):
-        decoded_url = urllib.parse.unquote(url)
-        try:
-            response = ssrf_proxy.head(decoded_url)
-            return {
-                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
-                "file_length": int(response.headers.get("Content-Length", 0)),
-            }
-        except Exception as e:
-            return {"error": str(e)}, 400
-
-
-api.add_resource(FileApi, "/files/upload")
-api.add_resource(FilePreviewApi, "/files/<uuid:file_id>/preview")
-api.add_resource(FileSupportTypeApi, "/files/support-type")
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")

api/controllers/console/files/errors.py

@@ -0,0 +1,25 @@
+from libs.exception import BaseHTTPException
+
+
+class FileTooLargeError(BaseHTTPException):
+    error_code = "file_too_large"
+    description = "File size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = "unsupported_file_type"
+    description = "File type not allowed."
+    code = 415
+
+
+class TooManyFilesError(BaseHTTPException):
+    error_code = "too_many_files"
+    description = "Only one file is allowed."
+    code = 400
+
+
+class NoFileUploadedError(BaseHTTPException):
+    error_code = "no_file_uploaded"
+    description = "Please upload your file."
+    code = 400

api/controllers/console/remote_files.py

@@ -0,0 +1,71 @@
+import urllib.parse
+from typing import cast
+
+from flask_login import current_user
+from flask_restful import Resource, marshal_with, reqparse
+
+from controllers.common import helpers
+from core.file import helpers as file_helpers
+from core.helper import ssrf_proxy
+from fields.file_fields import file_fields_with_signed_url, remote_file_info_fields
+from models.account import Account
+from services.file_service import FileService
+
+
+class RemoteFileInfoApi(Resource):
+    @marshal_with(remote_file_info_fields)
+    def get(self, url):
+        decoded_url = urllib.parse.unquote(url)
+        try:
+            response = ssrf_proxy.head(decoded_url)
+            return {
+                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
+                "file_length": int(response.headers.get("Content-Length", 0)),
+            }
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+
+class RemoteFileUploadApi(Resource):
+    @marshal_with(file_fields_with_signed_url)
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("url", type=str, required=True, help="URL is required")
+        args = parser.parse_args()
+
+        url = args["url"]
+
+        response = ssrf_proxy.head(url)
+        response.raise_for_status()
+
+        file_info = helpers.guess_file_info_from_response(response)
+
+        if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
+            return {"error": "File size exceeded"}, 400
+
+        response = ssrf_proxy.get(url)
+        response.raise_for_status()
+        content = response.content
+
+        try:
+            user = cast(Account, current_user)
+            upload_file = FileService.upload_file(
+                filename=file_info.filename,
+                content=content,
+                mimetype=file_info.mimetype,
+                user=user,
+                source_url=url,
+            )
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+        return {
+            "id": upload_file.id,
+            "name": upload_file.name,
+            "size": upload_file.size,
+            "extension": upload_file.extension,
+            "url": file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
+            "mime_type": upload_file.mime_type,
+            "created_by": upload_file.created_by,
+            "created_at": upload_file.created_at,
+        }, 201

api/controllers/console/setup.py

@@ -1,5 +1,3 @@
-from functools import wraps
-
 from flask import request
 from flask_restful import Resource, reqparse
 
@@ -10,7 +8,7 @@ from models.model import DifySetup
 from services.account_service import RegisterService, TenantService
 
 from . import api
-from .error import AlreadySetupError, NotInitValidateError, NotSetupError
+from .error import AlreadySetupError, NotInitValidateError
 from .init_validate import get_init_validate_status
 from .wraps import only_edition_self_hosted
 
@@ -52,26 +50,10 @@ class SetupApi(Resource):
         return {"result": "success"}, 201
 
 
-def setup_required(view):
-    @wraps(view)
-    def decorated(*args, **kwargs):
-        # check setup
-        if not get_init_validate_status():
-            raise NotInitValidateError()
-
-        elif not get_setup_status():
-            raise NotSetupError()
-
-        return view(*args, **kwargs)
-
-    return decorated
-
-
 def get_setup_status():
     if dify_config.EDITION == "SELF_HOSTED":
         return DifySetup.query.first()
-    else:
-        return True
+    return True
 
 
 api.add_resource(SetupApi, "/setup")

api/controllers/console/tag/tags.py

@@ -4,8 +4,7 @@ from flask_restful import Resource, marshal_with, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from fields.tag_fields import tag_fields
 from libs.login import login_required
 from models.model import Tag

api/controllers/console/workspace/account.py

@@ -8,14 +8,13 @@ from flask_restful import Resource, fields, marshal_with, reqparse
 from configs import dify_config
 from constants.languages import supported_language
 from controllers.console import api
-from controllers.console.setup import setup_required
 from controllers.console.workspace.error import (
     AccountAlreadyInitedError,
     CurrentPasswordIncorrectError,
     InvalidInvitationCodeError,
     RepeatPasswordNotMatchError,
 )
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from extensions.ext_database import db
 from fields.member_fields import account_fields
 from libs.helper import TimestampField, timezone

api/controllers/console/workspace/load_balancing_config.py

@@ -2,8 +2,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from libs.login import current_user, login_required

api/controllers/console/workspace/members.py

@@ -4,8 +4,11 @@ from flask_restful import Resource, abort, marshal_with, reqparse
 import services
 from configs import dify_config
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from extensions.ext_database import db
 from fields.member_fields import account_with_role_list_fields
 from libs.login import login_required

api/controllers/console/workspace/model_providers.py

@@ -6,8 +6,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.utils.encoders import jsonable_encoder

api/controllers/console/workspace/models.py

@@ -5,8 +5,7 @@ from flask_restful import Resource, reqparse
 from werkzeug.exceptions import Forbidden
 
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.entities.model_entities import ModelType
 from core.model_runtime.errors.validate import CredentialsValidateFailedError
 from core.model_runtime.utils.encoders import jsonable_encoder

api/controllers/console/workspace/tool_providers.py

@@ -7,8 +7,7 @@ from werkzeug.exceptions import Forbidden
 
 from configs import dify_config
 from controllers.console import api
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required
+from controllers.console.wraps import account_initialization_required, setup_required
 from core.model_runtime.utils.encoders import jsonable_encoder
 from libs.helper import alphanumeric, uuid_value
 from libs.login import login_required

api/controllers/console/workspace/workspace.py

@@ -6,6 +6,7 @@ from flask_restful import Resource, fields, inputs, marshal, marshal_with, reqpa
 from werkzeug.exceptions import Unauthorized
 
 import services
+from controllers.common.errors import FilenameNotExistsError
 from controllers.console import api
 from controllers.console.admin import admin_required
 from controllers.console.datasets.error import (
@@ -15,8 +16,11 @@ from controllers.console.datasets.error import (
     UnsupportedFileTypeError,
 )
 from controllers.console.error import AccountNotLinkTenantError
-from controllers.console.setup import setup_required
-from controllers.console.wraps import account_initialization_required, cloud_edition_billing_resource_check
+from controllers.console.wraps import (
+    account_initialization_required,
+    cloud_edition_billing_resource_check,
+    setup_required,
+)
 from extensions.ext_database import db
 from libs.helper import TimestampField
 from libs.login import login_required
@@ -193,12 +197,20 @@ class WebappLogoWorkspaceApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
 
+        if not file.filename:
+            raise FilenameNotExistsError
+
         extension = file.filename.split(".")[-1]
         if extension.lower() not in {"svg", "png"}:
             raise UnsupportedFileTypeError()
 
         try:
-            upload_file = FileService.upload_file(file=file, user=current_user)
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+            )
 
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)

api/controllers/console/wraps.py

@@ -1,4 +1,5 @@
 import json
+import os
 from functools import wraps
 
 from flask import abort, request
@@ -6,9 +7,12 @@ from flask_login import current_user
 
 from configs import dify_config
 from controllers.console.workspace.error import AccountNotInitializedError
+from models.model import DifySetup
 from services.feature_service import FeatureService
 from services.operation_service import OperationService
 
+from .error import NotInitValidateError, NotSetupError
+
 
 def account_initialization_required(view):
     @wraps(view)
@@ -124,3 +128,17 @@ def cloud_utm_record(view):
         return view(*args, **kwargs)
 
     return decorated
+
+
+def setup_required(view):
+    @wraps(view)
+    def decorated(*args, **kwargs):
+        # check setup
+        if dify_config.EDITION == "SELF_HOSTED" and os.environ.get("INIT_PASSWORD") and not DifySetup.query.first():
+            raise NotInitValidateError()
+        elif dify_config.EDITION == "SELF_HOSTED" and not DifySetup.query.first():
+            raise NotSetupError()
+
+        return view(*args, **kwargs)
+
+    return decorated

api/controllers/inner_api/workspace/workspace.py

@@ -1,6 +1,6 @@
 from flask_restful import Resource, reqparse
 
-from controllers.console.setup import setup_required
+from controllers.console.wraps import setup_required
 from controllers.inner_api import api
 from controllers.inner_api.wraps import inner_api_only
 from events.tenant_event import tenant_was_created

api/controllers/service_api/app/file.py

@@ -2,6 +2,7 @@ from flask import request
 from flask_restful import Resource, marshal_with
 
 import services
+from controllers.common.errors import FilenameNotExistsError
 from controllers.service_api import api
 from controllers.service_api.app.error import (
     FileTooLargeError,
@@ -31,8 +32,17 @@ class FileApi(Resource):
         if len(request.files) > 1:
             raise TooManyFilesError()
 
+        if not file.filename:
+            raise FilenameNotExistsError
+
         try:
-            upload_file = FileService.upload_file(file, end_user)
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=end_user,
+                source="datasets",
+            )
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)
         except services.errors.file.UnsupportedFileTypeError:

api/controllers/service_api/dataset/document.py

@@ -6,6 +6,7 @@ from sqlalchemy import desc
 from werkzeug.exceptions import NotFound
 
 import services.dataset_service
+from controllers.common.errors import FilenameNotExistsError
 from controllers.service_api import api
 from controllers.service_api.app.error import ProviderNotInitializeError
 from controllers.service_api.dataset.error import (
@@ -55,7 +56,12 @@ class DocumentAddByTextApi(DatasetApiResource):
         if not dataset.indexing_technique and not args["indexing_technique"]:
             raise ValueError("indexing_technique is required.")
 
-        upload_file = FileService.upload_text(args.get("text"), args.get("name"))
+        text = args.get("text")
+        name = args.get("name")
+        if text is None or name is None:
+            raise ValueError("Both 'text' and 'name' must be non-null values.")
+
+        upload_file = FileService.upload_text(text=str(text), text_name=str(name))
         data_source = {
             "type": "upload_file",
             "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
@@ -104,7 +110,11 @@ class DocumentUpdateByTextApi(DatasetApiResource):
             raise ValueError("Dataset is not exist.")
 
         if args["text"]:
-            upload_file = FileService.upload_text(args.get("text"), args.get("name"))
+            text = args.get("text")
+            name = args.get("name")
+            if text is None or name is None:
+                raise ValueError("Both text and name must be strings.")
+            upload_file = FileService.upload_text(text=str(text), text_name=str(name))
             data_source = {
                 "type": "upload_file",
                 "info_list": {"data_source_type": "upload_file", "file_info_list": {"file_ids": [upload_file.id]}},
@@ -163,7 +173,16 @@ class DocumentAddByFileApi(DatasetApiResource):
         if len(request.files) > 1:
             raise TooManyFilesError()
 
-        upload_file = FileService.upload_file(file, current_user)
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        upload_file = FileService.upload_file(
+            filename=file.filename,
+            content=file.read(),
+            mimetype=file.mimetype,
+            user=current_user,
+            source="datasets",
+        )
         data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
         args["data_source"] = data_source
         # validate args
@@ -212,7 +231,16 @@ class DocumentUpdateByFileApi(DatasetApiResource):
             if len(request.files) > 1:
                 raise TooManyFilesError()
 
-            upload_file = FileService.upload_file(file, current_user)
+            if not file.filename:
+                raise FilenameNotExistsError
+
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=current_user,
+                source="datasets",
+            )
             data_source = {"type": "upload_file", "info_list": {"file_info_list": {"file_ids": [upload_file.id]}}}
             args["data_source"] = data_source
         # validate args

api/controllers/web/__init__.py

@@ -2,8 +2,17 @@ from flask import Blueprint
 
 from libs.external_api import ExternalApi
 
+from .files import FileApi
+from .remote_files import RemoteFileInfoApi, RemoteFileUploadApi
+
 bp = Blueprint("web", __name__, url_prefix="/api")
 api = ExternalApi(bp)
 
+# Files
+api.add_resource(FileApi, "/files/upload")
 
-from . import app, audio, completion, conversation, feature, file, message, passport, saved_message, site, workflow
+# Remote files
+api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")
+api.add_resource(RemoteFileUploadApi, "/remote-files/upload")
+
+from . import app, audio, completion, conversation, feature, message, passport, saved_message, site, workflow

api/controllers/web/file.py

@@ -1,56 +0,0 @@
-import urllib.parse
-
-from flask import request
-from flask_restful import marshal_with, reqparse
-
-import services
-from controllers.web import api
-from controllers.web.error import FileTooLargeError, NoFileUploadedError, TooManyFilesError, UnsupportedFileTypeError
-from controllers.web.wraps import WebApiResource
-from core.helper import ssrf_proxy
-from fields.file_fields import file_fields, remote_file_info_fields
-from services.file_service import FileService
-
-
-class FileApi(WebApiResource):
-    @marshal_with(file_fields)
-    def post(self, app_model, end_user):
-        # get file from request
-        file = request.files["file"]
-
-        parser = reqparse.RequestParser()
-        parser.add_argument("source", type=str, required=False, location="args")
-        source = parser.parse_args().get("source")
-
-        # check file
-        if "file" not in request.files:
-            raise NoFileUploadedError()
-
-        if len(request.files) > 1:
-            raise TooManyFilesError()
-        try:
-            upload_file = FileService.upload_file(file=file, user=end_user, source=source)
-        except services.errors.file.FileTooLargeError as file_too_large_error:
-            raise FileTooLargeError(file_too_large_error.description)
-        except services.errors.file.UnsupportedFileTypeError:
-            raise UnsupportedFileTypeError()
-
-        return upload_file, 201
-
-
-class RemoteFileInfoApi(WebApiResource):
-    @marshal_with(remote_file_info_fields)
-    def get(self, url):
-        decoded_url = urllib.parse.unquote(url)
-        try:
-            response = ssrf_proxy.head(decoded_url)
-            return {
-                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
-                "file_length": int(response.headers.get("Content-Length", -1)),
-            }
-        except Exception as e:
-            return {"error": str(e)}, 400
-
-
-api.add_resource(FileApi, "/files/upload")
-api.add_resource(RemoteFileInfoApi, "/remote-files/<path:url>")

api/controllers/web/files.py

@@ -0,0 +1,43 @@
+from flask import request
+from flask_restful import marshal_with
+
+import services
+from controllers.common.errors import FilenameNotExistsError
+from controllers.web.error import FileTooLargeError, NoFileUploadedError, TooManyFilesError, UnsupportedFileTypeError
+from controllers.web.wraps import WebApiResource
+from fields.file_fields import file_fields
+from services.file_service import FileService
+
+
+class FileApi(WebApiResource):
+    @marshal_with(file_fields)
+    def post(self, app_model, end_user):
+        file = request.files["file"]
+        source = request.form.get("source")
+
+        if "file" not in request.files:
+            raise NoFileUploadedError()
+
+        if len(request.files) > 1:
+            raise TooManyFilesError()
+
+        if not file.filename:
+            raise FilenameNotExistsError
+
+        if source not in ("datasets", None):
+            source = None
+
+        try:
+            upload_file = FileService.upload_file(
+                filename=file.filename,
+                content=file.read(),
+                mimetype=file.mimetype,
+                user=end_user,
+                source=source,
+            )
+        except services.errors.file.FileTooLargeError as file_too_large_error:
+            raise FileTooLargeError(file_too_large_error.description)
+        except services.errors.file.UnsupportedFileTypeError:
+            raise UnsupportedFileTypeError()
+
+        return upload_file, 201

api/controllers/web/remote_files.py

@@ -0,0 +1,69 @@
+import urllib.parse
+
+from flask_login import current_user
+from flask_restful import marshal_with, reqparse
+
+from controllers.common import helpers
+from controllers.web.wraps import WebApiResource
+from core.file import helpers as file_helpers
+from core.helper import ssrf_proxy
+from fields.file_fields import file_fields_with_signed_url, remote_file_info_fields
+from services.file_service import FileService
+
+
+class RemoteFileInfoApi(WebApiResource):
+    @marshal_with(remote_file_info_fields)
+    def get(self, url):
+        decoded_url = urllib.parse.unquote(url)
+        try:
+            response = ssrf_proxy.head(decoded_url)
+            return {
+                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
+                "file_length": int(response.headers.get("Content-Length", -1)),
+            }
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+
+class RemoteFileUploadApi(WebApiResource):
+    @marshal_with(file_fields_with_signed_url)
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("url", type=str, required=True, help="URL is required")
+        args = parser.parse_args()
+
+        url = args["url"]
+
+        response = ssrf_proxy.head(url)
+        response.raise_for_status()
+
+        file_info = helpers.guess_file_info_from_response(response)
+
+        if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
+            return {"error": "File size exceeded"}, 400
+
+        response = ssrf_proxy.get(url)
+        response.raise_for_status()
+        content = response.content
+
+        try:
+            upload_file = FileService.upload_file(
+                filename=file_info.filename,
+                content=content,
+                mimetype=file_info.mimetype,
+                user=current_user,
+                source_url=url,
+            )
+        except Exception as e:
+            return {"error": str(e)}, 400
+
+        return {
+            "id": upload_file.id,
+            "name": upload_file.name,
+            "size": upload_file.size,
+            "extension": upload_file.extension,
+            "url": file_helpers.get_signed_file_url(upload_file_id=upload_file.id),
+            "mime_type": upload_file.mime_type,
+            "created_by": upload_file.created_by,
+            "created_at": upload_file.created_at,
+        }, 201

api/factories/file_factory.py

@@ -160,7 +160,7 @@ def _build_from_local_file(
         tenant_id=tenant_id,
         type=file_type,
         transfer_method=transfer_method,
-        remote_url=None,
+        remote_url=row.source_url,
         related_id=mapping.get("upload_file_id"),
         _extra_config=config,
         size=row.size,

api/fields/file_fields.py

@@ -24,3 +24,15 @@ remote_file_info_fields = {
     "file_type": fields.String(attribute="file_type"),
     "file_length": fields.Integer(attribute="file_length"),
 }
+
+
+file_fields_with_signed_url = {
+    "id": fields.String,
+    "name": fields.String,
+    "size": fields.Integer,
+    "extension": fields.String,
+    "url": fields.String,
+    "mime_type": fields.String,
+    "created_by": fields.String,
+    "created_at": TimestampField,
+}

api/migrations/versions/04c602f5dc9b_update_appmodelconfig_and_add_table_.py

@@ -28,16 +28,12 @@ def upgrade():
     sa.Column('updated_at', sa.DateTime(), server_default=sa.text('now()'), nullable=False),
     sa.PrimaryKeyConstraint('id', name='tracing_app_config_pkey')
     )
-    with op.batch_alter_table('tracing_app_configs', schema=None) as batch_op:
-        batch_op.create_index('tracing_app_config_app_id_idx', ['app_id'], unique=False)
 
     # ### end Alembic commands ###
 
 
 def downgrade():
     # ### commands auto generated by Alembic - please adjust! ##
-    with op.batch_alter_table('tracing_app_configs', schema=None) as batch_op:
-        batch_op.drop_index('tracing_app_config_app_id_idx')
-
     op.drop_table('tracing_app_configs')
+
     # ### end Alembic commands ###

api/migrations/versions/2024_11_01_0434-d3f6769a94a3_add_upload_files_source_url.py

@@ -0,0 +1,31 @@
+"""Add upload_files.source_url
+
+Revision ID: d3f6769a94a3
+Revises: 43fa78bc3b7d
+Create Date: 2024-11-01 04:34:23.816198
+
+"""
+from alembic import op
+import models as models
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = 'd3f6769a94a3'
+down_revision = '43fa78bc3b7d'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('upload_files', schema=None) as batch_op:
+        batch_op.add_column(sa.Column('source_url', sa.String(length=255), server_default='', nullable=False))
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('upload_files', schema=None) as batch_op:
+        batch_op.drop_column('source_url')
+    # ### end Alembic commands ###

api/migrations/versions/2024_11_01_0449-93ad8c19c40b_rename_conversation_variables_index_name.py

@@ -0,0 +1,52 @@
+"""rename conversation variables index name
+
+Revision ID: 93ad8c19c40b
+Revises: d3f6769a94a3
+Create Date: 2024-11-01 04:49:53.100250
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = '93ad8c19c40b'
+down_revision = 'd3f6769a94a3'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    conn = op.get_bind()
+    if conn.dialect.name == 'postgresql':
+        # Rename indexes for PostgreSQL
+        op.execute('ALTER INDEX workflow__conversation_variables_app_id_idx RENAME TO workflow_conversation_variables_app_id_idx')
+        op.execute('ALTER INDEX workflow__conversation_variables_created_at_idx RENAME TO workflow_conversation_variables_created_at_idx')
+    else:
+        # For other databases, use the original drop and create method
+        with op.batch_alter_table('workflow_conversation_variables', schema=None) as batch_op:
+            batch_op.drop_index('workflow__conversation_variables_app_id_idx')
+            batch_op.drop_index('workflow__conversation_variables_created_at_idx')
+            batch_op.create_index(batch_op.f('workflow_conversation_variables_app_id_idx'), ['app_id'], unique=False)
+            batch_op.create_index(batch_op.f('workflow_conversation_variables_created_at_idx'), ['created_at'], unique=False)
+
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    conn = op.get_bind()
+    if conn.dialect.name == 'postgresql':
+        # Rename indexes back for PostgreSQL
+        op.execute('ALTER INDEX workflow_conversation_variables_app_id_idx RENAME TO workflow__conversation_variables_app_id_idx')
+        op.execute('ALTER INDEX workflow_conversation_variables_created_at_idx RENAME TO workflow__conversation_variables_created_at_idx')
+    else:
+        # For other databases, use the original drop and create method
+        with op.batch_alter_table('workflow_conversation_variables', schema=None) as batch_op:
+            batch_op.drop_index(batch_op.f('workflow_conversation_variables_created_at_idx'))
+            batch_op.drop_index(batch_op.f('workflow_conversation_variables_app_id_idx'))
+            batch_op.create_index('workflow__conversation_variables_created_at_idx', ['created_at'], unique=False)
+            batch_op.create_index('workflow__conversation_variables_app_id_idx', ['app_id'], unique=False)
+
+    # ### end Alembic commands ###

api/migrations/versions/2024_11_01_0540-f4d7ce70a7ca_update_upload_files_source_url.py

@@ -0,0 +1,41 @@
+"""update upload_files.source_url
+
+Revision ID: f4d7ce70a7ca
+Revises: 93ad8c19c40b
+Create Date: 2024-11-01 05:40:03.531751
+
+"""
+from alembic import op
+import models as models
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = 'f4d7ce70a7ca'
+down_revision = '93ad8c19c40b'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('upload_files', schema=None) as batch_op:
+        batch_op.alter_column('source_url',
+               existing_type=sa.VARCHAR(length=255),
+               type_=sa.TEXT(),
+               existing_nullable=False,
+               existing_server_default=sa.text("''::character varying"))
+
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('upload_files', schema=None) as batch_op:
+        batch_op.alter_column('source_url',
+               existing_type=sa.TEXT(),
+               type_=sa.VARCHAR(length=255),
+               existing_nullable=False,
+               existing_server_default=sa.text("''::character varying"))
+
+    # ### end Alembic commands ###

api/migrations/versions/2024_11_01_0622-d07474999927_update_type_of_custom_disclaimer_to_text.py

@@ -0,0 +1,67 @@
+"""update type of custom_disclaimer to TEXT
+
+Revision ID: d07474999927
+Revises: f4d7ce70a7ca
+Create Date: 2024-11-01 06:22:27.981398
+
+"""
+from alembic import op
+import models as models
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = 'd07474999927'
+down_revision = 'f4d7ce70a7ca'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.execute("UPDATE recommended_apps SET custom_disclaimer = '' WHERE custom_disclaimer IS NULL")
+    op.execute("UPDATE sites SET custom_disclaimer = '' WHERE custom_disclaimer IS NULL")
+    op.execute("UPDATE tool_api_providers SET custom_disclaimer = '' WHERE custom_disclaimer IS NULL")
+
+    with op.batch_alter_table('recommended_apps', schema=None) as batch_op:
+        batch_op.alter_column('custom_disclaimer',
+               existing_type=sa.VARCHAR(length=255),
+               type_=sa.TEXT(),
+               nullable=False)
+
+    with op.batch_alter_table('sites', schema=None) as batch_op:
+        batch_op.alter_column('custom_disclaimer',
+               existing_type=sa.VARCHAR(length=255),
+               type_=sa.TEXT(),
+               nullable=False)
+
+    with op.batch_alter_table('tool_api_providers', schema=None) as batch_op:
+        batch_op.alter_column('custom_disclaimer',
+               existing_type=sa.VARCHAR(length=255),
+               type_=sa.TEXT(),
+               nullable=False)
+
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('tool_api_providers', schema=None) as batch_op:
+        batch_op.alter_column('custom_disclaimer',
+               existing_type=sa.TEXT(),
+               type_=sa.VARCHAR(length=255),
+               nullable=True)
+
+    with op.batch_alter_table('sites', schema=None) as batch_op:
+        batch_op.alter_column('custom_disclaimer',
+               existing_type=sa.TEXT(),
+               type_=sa.VARCHAR(length=255),
+               nullable=True)
+
+    with op.batch_alter_table('recommended_apps', schema=None) as batch_op:
+        batch_op.alter_column('custom_disclaimer',
+               existing_type=sa.TEXT(),
+               type_=sa.VARCHAR(length=255),
+               nullable=True)
+
+    # ### end Alembic commands ###

api/migrations/versions/2024_11_01_0623-09a8d1878d9b_update_workflows_graph_features_and_.py

@@ -0,0 +1,75 @@
+"""update workflows graph, features and updated_at
+
+Revision ID: 09a8d1878d9b
+Revises: d07474999927
+Create Date: 2024-11-01 06:23:59.579186
+
+"""
+from alembic import op
+import models as models
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = '09a8d1878d9b'
+down_revision = 'd07474999927'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('conversations', schema=None) as batch_op:
+        batch_op.alter_column('inputs',
+               existing_type=postgresql.JSON(astext_type=sa.Text()),
+               nullable=False)
+
+    with op.batch_alter_table('messages', schema=None) as batch_op:
+        batch_op.alter_column('inputs',
+               existing_type=postgresql.JSON(astext_type=sa.Text()),
+               nullable=False)
+
+    op.execute("UPDATE workflows SET updated_at = created_at WHERE updated_at IS NULL")
+    op.execute("UPDATE workflows SET graph = '' WHERE graph IS NULL")
+    op.execute("UPDATE workflows SET features = '' WHERE features IS NULL")
+
+    with op.batch_alter_table('workflows', schema=None) as batch_op:
+        batch_op.alter_column('graph',
+               existing_type=sa.TEXT(),
+               nullable=False)
+        batch_op.alter_column('features',
+               existing_type=sa.TEXT(),
+               type_=sa.String(),
+               nullable=False)
+        batch_op.alter_column('updated_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=False)
+
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    with op.batch_alter_table('workflows', schema=None) as batch_op:
+        batch_op.alter_column('updated_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=True)
+        batch_op.alter_column('features',
+               existing_type=sa.String(),
+               type_=sa.TEXT(),
+               nullable=True)
+        batch_op.alter_column('graph',
+               existing_type=sa.TEXT(),
+               nullable=True)
+
+    with op.batch_alter_table('messages', schema=None) as batch_op:
+        batch_op.alter_column('inputs',
+               existing_type=postgresql.JSON(astext_type=sa.Text()),
+               nullable=True)
+
+    with op.batch_alter_table('conversations', schema=None) as batch_op:
+        batch_op.alter_column('inputs',
+               existing_type=postgresql.JSON(astext_type=sa.Text()),
+               nullable=True)
+
+    # ### end Alembic commands ###

api/migrations/versions/2a3aebbbf4bb_add_app_tracing.py

@@ -22,17 +22,11 @@ def upgrade():
     with op.batch_alter_table('apps', schema=None) as batch_op:
         batch_op.add_column(sa.Column('tracing', sa.Text(), nullable=True))
 
-    with op.batch_alter_table('trace_app_config', schema=None) as batch_op:
-        batch_op.create_index('tracing_app_config_app_id_idx', ['app_id'], unique=False)
-
     # ### end Alembic commands ###
 
 
 def downgrade():
     # ### commands auto generated by Alembic - please adjust! ###
-    with op.batch_alter_table('trace_app_config', schema=None) as batch_op:
-        batch_op.drop_index('tracing_app_config_app_id_idx')
-
     with op.batch_alter_table('apps', schema=None) as batch_op:
         batch_op.drop_column('tracing')
 

api/migrations/versions/c031d46af369_remove_app_model_config_trace_config_.py

@@ -30,30 +30,15 @@ def upgrade():
     sa.Column('is_active', sa.Boolean(), server_default=sa.text('true'), nullable=False),
                     sa.PrimaryKeyConstraint('id', name='trace_app_config_pkey')
     )
+
     with op.batch_alter_table('trace_app_config', schema=None) as batch_op:
         batch_op.create_index('trace_app_config_app_id_idx', ['app_id'], unique=False)
 
-    with op.batch_alter_table('tracing_app_configs', schema=None) as batch_op:
-        batch_op.drop_index('tracing_app_config_app_id_idx')
     # ### end Alembic commands ###
 
 
 def downgrade():
     # ### commands auto generated by Alembic - please adjust! ###
-    op.create_table('tracing_app_configs',
-    sa.Column('id', sa.UUID(), server_default=sa.text('uuid_generate_v4()'), autoincrement=False, nullable=False),
-    sa.Column('app_id', sa.UUID(), autoincrement=False, nullable=False),
-    sa.Column('tracing_provider', sa.VARCHAR(length=255), autoincrement=False, nullable=True),
-    sa.Column('tracing_config', postgresql.JSON(astext_type=sa.Text()), autoincrement=False, nullable=True),
-    sa.Column('created_at', postgresql.TIMESTAMP(), server_default=sa.text('now()'), autoincrement=False, nullable=False),
-    sa.Column('updated_at', postgresql.TIMESTAMP(), server_default=sa.text('now()'), autoincrement=False, nullable=False),
-                    sa.PrimaryKeyConstraint('id', name='trace_app_config_pkey')
-    )
-    with op.batch_alter_table('tracing_app_configs', schema=None) as batch_op:
-        batch_op.create_index('trace_app_config_app_id_idx', ['app_id'], unique=False)
-
-    with op.batch_alter_table('trace_app_config', schema=None) as batch_op:
-        batch_op.drop_index('trace_app_config_app_id_idx')
-
     op.drop_table('trace_app_config')
+
     # ### end Alembic commands ###

api/migrations/versions/fecff1c3da27_remove_extra_tracing_app_config_table .py

@@ -20,12 +20,10 @@ def upgrade():
     # ### commands auto generated by Alembic - please adjust! ###
     op.drop_table('tracing_app_configs')
 
-    with op.batch_alter_table('trace_app_config', schema=None) as batch_op:
-        batch_op.drop_index('tracing_app_config_app_id_idx')
-
     # idx_dataset_permissions_tenant_id
     with op.batch_alter_table('dataset_permissions', schema=None) as batch_op:
         batch_op.create_index('idx_dataset_permissions_tenant_id', ['tenant_id'])
+
     # ### end Alembic commands ###
 
 
@@ -46,9 +44,7 @@ def downgrade():
         sa.PrimaryKeyConstraint('id', name='tracing_app_config_pkey')
     )
 
-    with op.batch_alter_table('trace_app_config', schema=None) as batch_op:
-        batch_op.create_index('tracing_app_config_app_id_idx', ['app_id'])
-
     with op.batch_alter_table('dataset_permissions', schema=None) as batch_op:
         batch_op.drop_index('idx_dataset_permissions_tenant_id')
+
     # ### end Alembic commands ###

api/models/model.py

@@ -6,6 +6,7 @@ from datetime import datetime
 from enum import Enum
 from typing import Any, Literal, Optional
 
+import sqlalchemy as sa
 from flask import request
 from flask_login import UserMixin
 from pydantic import BaseModel, Field
@@ -483,7 +484,7 @@ class RecommendedApp(db.Model):
     description = db.Column(db.JSON, nullable=False)
     copyright = db.Column(db.String(255), nullable=False)
     privacy_policy = db.Column(db.String(255), nullable=False)
-    custom_disclaimer = db.Column(db.String(255), nullable=True)
+    custom_disclaimer: Mapped[str] = mapped_column(sa.TEXT, default="")
     category = db.Column(db.String(255), nullable=False)
     position = db.Column(db.Integer, nullable=False, default=0)
     is_listed = db.Column(db.Boolean, nullable=False, default=True)
@@ -1306,7 +1307,7 @@ class Site(db.Model):
     privacy_policy = db.Column(db.String(255))
     show_workflow_steps = db.Column(db.Boolean, nullable=False, server_default=db.text("true"))
     use_icon_as_answer_icon = db.Column(db.Boolean, nullable=False, server_default=db.text("false"))
-    custom_disclaimer = db.Column(db.String(255), nullable=True)
+    custom_disclaimer: Mapped[str] = mapped_column(sa.TEXT, default="")
     customize_domain = db.Column(db.String(255))
     customize_token_strategy = db.Column(db.String(255), nullable=False)
     prompt_public = db.Column(db.Boolean, nullable=False, server_default=db.text("false"))
@@ -1384,6 +1385,7 @@ class UploadFile(db.Model):
     used_by: Mapped[str | None] = db.Column(StringUUID, nullable=True)
     used_at: Mapped[datetime | None] = db.Column(db.DateTime, nullable=True)
     hash: Mapped[str | None] = db.Column(db.String(255), nullable=True)
+    source_url: Mapped[str] = mapped_column(sa.TEXT, default="")
 
     def __init__(
         self,
@@ -1402,7 +1404,8 @@ class UploadFile(db.Model):
         used_by: str | None = None,
         used_at: datetime | None = None,
         hash: str | None = None,
-    ) -> None:
+        source_url: str = "",
+    ):
         self.tenant_id = tenant_id
         self.storage_type = storage_type
         self.key = key
@@ -1417,6 +1420,7 @@ class UploadFile(db.Model):
         self.used_by = used_by
         self.used_at = used_at
         self.hash = hash
+        self.source_url = source_url
 
 
 class ApiRequest(db.Model):

api/models/tools.py

@@ -1,6 +1,7 @@
 import json
 from typing import Optional
 
+import sqlalchemy as sa
 from sqlalchemy import ForeignKey
 from sqlalchemy.orm import Mapped, mapped_column
 
@@ -117,7 +118,7 @@ class ApiToolProvider(db.Model):
     # privacy policy
     privacy_policy = db.Column(db.String(255), nullable=True)
     # custom_disclaimer
-    custom_disclaimer = db.Column(db.String(255), nullable=True)
+    custom_disclaimer: Mapped[str] = mapped_column(sa.TEXT, default="")
 
     created_at = db.Column(db.DateTime, nullable=False, server_default=db.text("CURRENT_TIMESTAMP(0)"))
     updated_at = db.Column(db.DateTime, nullable=False, server_default=db.text("CURRENT_TIMESTAMP(0)"))

api/models/workflow.py

@@ -105,8 +105,8 @@ class Workflow(db.Model):
     created_at: Mapped[datetime] = mapped_column(
         db.DateTime, nullable=False, server_default=db.text("CURRENT_TIMESTAMP(0)")
     )
-    updated_by: Mapped[str] = mapped_column(StringUUID)
-    updated_at: Mapped[datetime] = mapped_column(db.DateTime)
+    updated_by: Mapped[Optional[str]] = mapped_column(StringUUID)
+    updated_at: Mapped[datetime] = mapped_column(db.DateTime, nullable=False)
     _environment_variables: Mapped[str] = mapped_column(
         "environment_variables", db.Text, nullable=False, server_default="{}"
     )

api/services/dataset_service.py

@@ -4,7 +4,7 @@ import logging
 import random
 import time
 import uuid
-from typing import Optional
+from typing import Any, Optional
 
 from flask_login import current_user
 from sqlalchemy import func
@@ -675,7 +675,7 @@ class DocumentService:
     def save_document_with_dataset_id(
         dataset: Dataset,
         document_data: dict,
-        account: Account,
+        account: Account | Any,
         dataset_process_rule: Optional[DatasetProcessRule] = None,
         created_from: str = "web",
     ):

api/services/file_service.py

@@ -1,10 +1,9 @@
 import datetime
 import hashlib
 import uuid
-from typing import Literal, Union
+from typing import Any, Literal, Union
 
 from flask_login import current_user
-from werkzeug.datastructures import FileStorage
 from werkzeug.exceptions import NotFound
 
 from configs import dify_config
@@ -21,7 +20,8 @@ from extensions.ext_storage import storage
 from models.account import Account
 from models.enums import CreatedByRole
 from models.model import EndUser, UploadFile
-from services.errors.file import FileNotExistsError, FileTooLargeError, UnsupportedFileTypeError
+
+from .errors.file import FileTooLargeError, UnsupportedFileTypeError
 
 PREVIEW_WORDS_LIMIT = 3000
 
@@ -29,12 +29,15 @@ PREVIEW_WORDS_LIMIT = 3000
 class FileService:
     @staticmethod
     def upload_file(
-        file: FileStorage, user: Union[Account, EndUser], source: Literal["datasets"] | None = None
+        *,
+        filename: str,
+        content: bytes,
+        mimetype: str,
+        user: Union[Account, EndUser, Any],
+        source: Literal["datasets"] | None = None,
+        source_url: str = "",
     ) -> UploadFile:
-        # get file name
-        filename = file.filename
-        if not filename:
-            raise FileNotExistsError
+        # get file extension
         extension = filename.split(".")[-1].lower()
         if len(filename) > 200:
             filename = filename.split(".")[0][:200] + "." + extension
@@ -42,25 +45,12 @@ class FileService:
         if source == "datasets" and extension not in DOCUMENT_EXTENSIONS:
             raise UnsupportedFileTypeError()
 
-        # select file size limit
-        if extension in IMAGE_EXTENSIONS:
-            file_size_limit = dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT * 1024 * 1024
-        elif extension in VIDEO_EXTENSIONS:
-            file_size_limit = dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT * 1024 * 1024
-        elif extension in AUDIO_EXTENSIONS:
-            file_size_limit = dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT * 1024 * 1024
-        else:
-            file_size_limit = dify_config.UPLOAD_FILE_SIZE_LIMIT * 1024 * 1024
-
-        # read file content
-        file_content = file.read()
         # get file size
-        file_size = len(file_content)
+        file_size = len(content)
 
         # check if the file size is exceeded
-        if file_size > file_size_limit:
-            message = f"File size exceeded. {file_size} > {file_size_limit}"
-            raise FileTooLargeError(message)
+        if not FileService.is_file_size_within_limit(extension=extension, file_size=file_size):
+            raise FileTooLargeError
 
         # generate file key
         file_uuid = str(uuid.uuid4())
@@ -74,7 +64,7 @@ class FileService:
         file_key = "upload_files/" + current_tenant_id + "/" + file_uuid + "." + extension
 
         # save file to storage
-        storage.save(file_key, file_content)
+        storage.save(file_key, content)
 
         # save file to db
         upload_file = UploadFile(
@@ -84,12 +74,13 @@ class FileService:
             name=filename,
             size=file_size,
             extension=extension,
-            mime_type=file.mimetype,
+            mime_type=mimetype,
             created_by_role=(CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER),
             created_by=user.id,
             created_at=datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
             used=False,
-            hash=hashlib.sha3_256(file_content).hexdigest(),
+            hash=hashlib.sha3_256(content).hexdigest(),
+            source_url=source_url,
         )
 
         db.session.add(upload_file)
@@ -97,6 +88,19 @@ class FileService:
 
         return upload_file
 
+    @staticmethod
+    def is_file_size_within_limit(*, extension: str, file_size: int) -> bool:
+        if extension in IMAGE_EXTENSIONS:
+            file_size_limit = dify_config.UPLOAD_IMAGE_FILE_SIZE_LIMIT * 1024 * 1024
+        elif extension in VIDEO_EXTENSIONS:
+            file_size_limit = dify_config.UPLOAD_VIDEO_FILE_SIZE_LIMIT * 1024 * 1024
+        elif extension in AUDIO_EXTENSIONS:
+            file_size_limit = dify_config.UPLOAD_AUDIO_FILE_SIZE_LIMIT * 1024 * 1024
+        else:
+            file_size_limit = dify_config.UPLOAD_FILE_SIZE_LIMIT * 1024 * 1024
+
+        return file_size <= file_size_limit
+
     @staticmethod
     def upload_text(text: str, text_name: str) -> UploadFile:
         if len(text_name) > 200: